-
Hi, I wanted to know if elektronn3 can load models trained/saved with elektronn2. |
Beta Was this translation helpful? Give feedback.
Answered by
mdraw
Feb 2, 2023
Replies: 1 comment
-
Hi, this is not straightforward because elektronn2 is based on Theano and elektronn3 is based on PyTorch. Theoretically you can export elektronn2 network weights to an equivalent PyTorch-based network by copying them by hand with NumPy but I would recommend just retraining from scratch with elektronn3 instead. |
Beta Was this translation helpful? Give feedback.
0 replies
Answer selected by
mdraw
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Hi, this is not straightforward because elektronn2 is based on Theano and elektronn3 is based on PyTorch. Theoretically you can export elektronn2 network weights to an equivalent PyTorch-based network by copying them by hand with NumPy but I would recommend just retraining from scratch with elektronn3 instead.